Feedback humano ou artificial? Comparando percepções de estudantes sobre feedback gerado por LLM e professores em atividades de POO
Resumo
Este trabalho comparou a percepção de estudantes sobre o feedback formativo elaborado pelo professor e o feedback gerado por uma LLM em uma atividade de Programação Orientada a Objetos. Apesar do feedback gerado pela LLM apresentar médias ligeiramente superiores em alguns constructos, a análise quantitativa baseada teste de Wilcoxon, não indicou diferenças estatisticamente significativas entre os dois tipos de feedback. A análise qualitativa mostrou que os estudantes perceberam o feedback da LLM como mais detalhado, explicativo e estruturado. Os resultados sugerem que as LLMs podem apoiar a prática docente, especialmente como ferramenta complementar para ampliar a oferta de feedback formativo em atividades de programação.
Palavras-chave:
Feedback Formativo, Modelos de Linguagem de Grande Escala, Programação Orientada a Objetos
Referências
Alyahyan, E., Bikanga Ada, M., and Lever, J. (2025). WIP: A Pedagogical Prompt Engineering Framework for LLM-Based Feedback in Higher Education (PPE-LLM). pages 1–5.
Barros, J., Moraes, L. O., Oliveira, F., and Delgado, C. A. D. M. (2025). Large Language Models Generating Feedback for Students of Introductory Programming Courses. In Cristea, A. I., Walker, E., Lu, Y., Santos, O. C., and Isotani, S., editors, Artificial Intelligence in Education, pages 421–433, Cham. Springer Nature Switzerland.
Batista, H. H. N., Cavalcanti, A. P., Miranda, P., Nascimento, A., and Mello, R. F. (2022). Classificação Multi-classe para Análise de Qualidade de Feedback. In Simpósio Brasileiro de Informática na Educação (SBIE), pages 1114–1125. SBC.
Brooks, C., Huang, Y., Hattie, J., Carroll, A., and Burton, R. (2019). What Is My Next Step? School Students' Perceptions of Feedback. Frontiers in Education, 4.
Carless, D. and Boud, D. (2018). The development of student feedback literacy: enabling uptake of feedback. Assessment & Evaluation in Higher Education, 43:1315–1325.
Cavalcanti, A. P., Mello, R. F., Miranda, P., Nascimento, A., and Freitas, F. (2021). Utilização de Recursos Linguísticos para Classificação Automática de Mensagens de Feedback. In Simpósio Brasileiro de Informática na Educação (SBIE), pages 861–872. SBC.
Cavalcanti, A. P., Rolim, V. B., Gašević, D., and Mello, R. F. (2023). A Comparative Analysis Between Good Feedback Descriptors on Online Courses. In Simpósio Brasileiro de Informática na Educação (SBIE), pages 1512–1523. SBC.
Dunn, T. J., Baguley, T., and Brunsden, V. (2014). From alpha to omega: a practical solution to the pervasive problem of internal consistency estimation. British Journal of Psychology, 105(3):399–412.
Efan, E., Krismadinata, K., Jama, J., and Mulya, R. (2023). A Systematic Literature Review of Teaching and Learning on Object-Oriented Programming Course. International Journal of Information and Education Technology, 13:302–312.
Er, E., Akçapınar, G., Bayazıt, A., Noroozi, O., and Banihashem, S. K. (2025). Assessing student perceptions and use of instructor versus AI-generated feedback. British Journal of Educational Technology, 56(3):1074–1091.
Hattie, J. and Timperley, H. (2007). The Power of Feedback. Review of Educational Research, 77(1):81–112.
Hodges, J. L. and Lehmann, E. L. (1963). Estimates of location based on rank tests. The Annals of Mathematical Statistics, 34(2):598–611.
Jacobsen, L. J. and Weber, K. E. (2025). The Promises and Pitfalls of Large Language Models as Feedback Providers: A Study of Prompt Engineering and the Quality of AI-Driven Feedback. AI, 6(2):35.
Keuning, H., Jeuring, J., and Heeren, B. (2018). A Systematic Literature Review of Automated Feedback Generation for Programming Exercises. ACM Transactions on Computing Education, 19:1–43.
Lipsch-Wijnen, I. and Dirkx, K. (2022). A case study of the use of the Hattie and Timperley feedback model on written feedback in thesis examination in higher education. Cogent Education, 9(1):2082089.
Lohr, D., Keuning, H., and Kiesler, N. (2024). You're (Not) My Type – Can LLMs Generate Feedback of Specific Types for Introductory Programming Tasks?
Mandouit, L. and Hattie, J. (2023). Revisiting "The Power of Feedback" from the perspective of the learner. Learning and Instruction, 84:101718.
Mueller, M., List, C., and Kipp, M. (2025). The Power of Context: An LLM-based Programming Tutor with Focused and Proactive Feedback. In Proceedings of the 6th European Conference on Software Engineering Education, ECSEE '25, pages 1–10, New York, NY, USA. Association for Computing Machinery.
Nguyen, H. and Allan, V. (2024). Using gpt-4 to provide tiered, formative code feedback. In Proceedings of the 55th ACM Technical Symposium on Computer Science Education V. 1, SIGCSE 2024, page 958–964, New York, NY, USA. Association for Computing Machinery.
Nicol, D. J. and Macfarlane-Dick, D. (2006). Formative assessment and self-regulated learning: a model and seven principles of good feedback practice. Studies in Higher Education, 31(2):199–218.
Osakwe, I., Chen, G., Whitelock-Wainwright, A., Gašević, D., Pinheiro Cavalcanti, A., and Ferreira Mello, R. (2022). Towards automated content analysis of educational feedback: A multi-language study. Computers and Education: Artificial Intelligence, 3:100059.
Ott, C., Robins, A., and Shephard, K. (2016). Translating Principles of Effective Feedback for Students into the CS1 Context. ACM Trans. Comput. Educ., 16(1):1:1–1:27.
Phung, T., Choi, H., Wu, M., Brooks, C., Gulwani, S., and Singla, A. (2025). Closing the Loop: An Instructor-in-the-Loop AI Assistance System for Supporting Student Help-Seeking in Programming Education. arXiv:2510.14457 [cs].
Shute, V. (2008). Focus on Formative Feedback. Review of Educational Research, 78:153–189.
Sidney, S. (1957). NONPARAMETRIC STATISTICS FOR THE BEHAVIORAL SCIENCES:. In The Journal of Nervous and Mental Disease, volume 125, page 497.
Silva, F. G. and Aranha, E. H. S. (2025). LLMs na Educação em Programação: Estratégias para Avaliação e Feedback Formativo. In Simpósio Brasileiro de Educação em Computação (EDUCOMP), pages 81–87. SBC.
Tang, X., Wong, S., Huynh, M., He, Z., Yang, Y., and Chen, Y. (2024). SPHERE: Scaling Personalized Feedback in Programming Classrooms with Structured Review of LLM Outputs. arXiv:2410.16513 [cs].
Xavier, C., da Costa, N. T., Valdo, A. K., Alves, G., Rodrigues, L., Rodrigues, L. F., Silva, M., Neto, R., Falcão, T. P., Gasevic, D., and Mello, R. F. (2026). Human Teacher vs. LLM-Generated Feedback in Secondary Education: A Comparative Study on Student Perceptions. In Tammets, K., Sosnovsky, S., Ferreira Mello, R., Pishtari, G., and Nazaretsky, T., editors, Two Decades of TEL. From Lessons Learnt to Challenges Ahead, pages 534–548, Cham. Springer Nature Switzerland.
Yousef, M., Mohamed, K., Medhat, W., Mohamed, E. H., Khoriba, G., and Arafa, T. (2025). BeGrading: large language models for enhanced feedback in programming education. Neural Computing and Applications, 37(2):1027–1040.
Yu, H. and Xie, Q. (2025). Generative AI vs. teachers: Feedback quality, feedback uptake, and revision. Language Teaching Research Quarterly, 47:113–137.
Barros, J., Moraes, L. O., Oliveira, F., and Delgado, C. A. D. M. (2025). Large Language Models Generating Feedback for Students of Introductory Programming Courses. In Cristea, A. I., Walker, E., Lu, Y., Santos, O. C., and Isotani, S., editors, Artificial Intelligence in Education, pages 421–433, Cham. Springer Nature Switzerland.
Batista, H. H. N., Cavalcanti, A. P., Miranda, P., Nascimento, A., and Mello, R. F. (2022). Classificação Multi-classe para Análise de Qualidade de Feedback. In Simpósio Brasileiro de Informática na Educação (SBIE), pages 1114–1125. SBC.
Brooks, C., Huang, Y., Hattie, J., Carroll, A., and Burton, R. (2019). What Is My Next Step? School Students' Perceptions of Feedback. Frontiers in Education, 4.
Carless, D. and Boud, D. (2018). The development of student feedback literacy: enabling uptake of feedback. Assessment & Evaluation in Higher Education, 43:1315–1325.
Cavalcanti, A. P., Mello, R. F., Miranda, P., Nascimento, A., and Freitas, F. (2021). Utilização de Recursos Linguísticos para Classificação Automática de Mensagens de Feedback. In Simpósio Brasileiro de Informática na Educação (SBIE), pages 861–872. SBC.
Cavalcanti, A. P., Rolim, V. B., Gašević, D., and Mello, R. F. (2023). A Comparative Analysis Between Good Feedback Descriptors on Online Courses. In Simpósio Brasileiro de Informática na Educação (SBIE), pages 1512–1523. SBC.
Dunn, T. J., Baguley, T., and Brunsden, V. (2014). From alpha to omega: a practical solution to the pervasive problem of internal consistency estimation. British Journal of Psychology, 105(3):399–412.
Efan, E., Krismadinata, K., Jama, J., and Mulya, R. (2023). A Systematic Literature Review of Teaching and Learning on Object-Oriented Programming Course. International Journal of Information and Education Technology, 13:302–312.
Er, E., Akçapınar, G., Bayazıt, A., Noroozi, O., and Banihashem, S. K. (2025). Assessing student perceptions and use of instructor versus AI-generated feedback. British Journal of Educational Technology, 56(3):1074–1091.
Hattie, J. and Timperley, H. (2007). The Power of Feedback. Review of Educational Research, 77(1):81–112.
Hodges, J. L. and Lehmann, E. L. (1963). Estimates of location based on rank tests. The Annals of Mathematical Statistics, 34(2):598–611.
Jacobsen, L. J. and Weber, K. E. (2025). The Promises and Pitfalls of Large Language Models as Feedback Providers: A Study of Prompt Engineering and the Quality of AI-Driven Feedback. AI, 6(2):35.
Keuning, H., Jeuring, J., and Heeren, B. (2018). A Systematic Literature Review of Automated Feedback Generation for Programming Exercises. ACM Transactions on Computing Education, 19:1–43.
Lipsch-Wijnen, I. and Dirkx, K. (2022). A case study of the use of the Hattie and Timperley feedback model on written feedback in thesis examination in higher education. Cogent Education, 9(1):2082089.
Lohr, D., Keuning, H., and Kiesler, N. (2024). You're (Not) My Type – Can LLMs Generate Feedback of Specific Types for Introductory Programming Tasks?
Mandouit, L. and Hattie, J. (2023). Revisiting "The Power of Feedback" from the perspective of the learner. Learning and Instruction, 84:101718.
Mueller, M., List, C., and Kipp, M. (2025). The Power of Context: An LLM-based Programming Tutor with Focused and Proactive Feedback. In Proceedings of the 6th European Conference on Software Engineering Education, ECSEE '25, pages 1–10, New York, NY, USA. Association for Computing Machinery.
Nguyen, H. and Allan, V. (2024). Using gpt-4 to provide tiered, formative code feedback. In Proceedings of the 55th ACM Technical Symposium on Computer Science Education V. 1, SIGCSE 2024, page 958–964, New York, NY, USA. Association for Computing Machinery.
Nicol, D. J. and Macfarlane-Dick, D. (2006). Formative assessment and self-regulated learning: a model and seven principles of good feedback practice. Studies in Higher Education, 31(2):199–218.
Osakwe, I., Chen, G., Whitelock-Wainwright, A., Gašević, D., Pinheiro Cavalcanti, A., and Ferreira Mello, R. (2022). Towards automated content analysis of educational feedback: A multi-language study. Computers and Education: Artificial Intelligence, 3:100059.
Ott, C., Robins, A., and Shephard, K. (2016). Translating Principles of Effective Feedback for Students into the CS1 Context. ACM Trans. Comput. Educ., 16(1):1:1–1:27.
Phung, T., Choi, H., Wu, M., Brooks, C., Gulwani, S., and Singla, A. (2025). Closing the Loop: An Instructor-in-the-Loop AI Assistance System for Supporting Student Help-Seeking in Programming Education. arXiv:2510.14457 [cs].
Shute, V. (2008). Focus on Formative Feedback. Review of Educational Research, 78:153–189.
Sidney, S. (1957). NONPARAMETRIC STATISTICS FOR THE BEHAVIORAL SCIENCES:. In The Journal of Nervous and Mental Disease, volume 125, page 497.
Silva, F. G. and Aranha, E. H. S. (2025). LLMs na Educação em Programação: Estratégias para Avaliação e Feedback Formativo. In Simpósio Brasileiro de Educação em Computação (EDUCOMP), pages 81–87. SBC.
Tang, X., Wong, S., Huynh, M., He, Z., Yang, Y., and Chen, Y. (2024). SPHERE: Scaling Personalized Feedback in Programming Classrooms with Structured Review of LLM Outputs. arXiv:2410.16513 [cs].
Xavier, C., da Costa, N. T., Valdo, A. K., Alves, G., Rodrigues, L., Rodrigues, L. F., Silva, M., Neto, R., Falcão, T. P., Gasevic, D., and Mello, R. F. (2026). Human Teacher vs. LLM-Generated Feedback in Secondary Education: A Comparative Study on Student Perceptions. In Tammets, K., Sosnovsky, S., Ferreira Mello, R., Pishtari, G., and Nazaretsky, T., editors, Two Decades of TEL. From Lessons Learnt to Challenges Ahead, pages 534–548, Cham. Springer Nature Switzerland.
Yousef, M., Mohamed, K., Medhat, W., Mohamed, E. H., Khoriba, G., and Arafa, T. (2025). BeGrading: large language models for enhanced feedback in programming education. Neural Computing and Applications, 37(2):1027–1040.
Yu, H. and Xie, Q. (2025). Generative AI vs. teachers: Feedback quality, feedback uptake, and revision. Language Teaching Research Quarterly, 47:113–137.
Publicado
05/10/2026
Como Citar
MELO, Marcel; RODRIGUES, Luiz; MELLO, Rafael Ferreira; XAVIER, Cleon; ARAÚJO, Rafael Dias.
Feedback humano ou artificial? Comparando percepções de estudantes sobre feedback gerado por LLM e professores em atividades de POO. In: SIMPÓSIO BRASILEIRO DE INFORMÁTICA NA EDUCAÇÃO (SBIE), 37. , 2026, Goiânia/GO.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 1843-1857.
DOI: https://doi.org/10.5753/sbie.2026.28113.
